English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate early congestion prediction can prevent unpleasant surprises at therouting stage, playing a crucial character in assisting designers to iteratefaster in VLSI design cycles. In this paper, we introduce a novel strategy tofully incorporate topological and geometrical features of circuits by makingseveral key designs in our network architecture. To be more specific, weconstruct two individual graphs (geometry-graph, topology-graph) with distinctedge construction schemes according to their unique properties. We then proposea dual-branch network with different encoder layers in each pathway andaggregate representations with a sophisticated fusion strategy. Our network,named HybridNet, not only provides a simple yet effective way to capture thegeometric interactions of cells, but also preserves the original topologicalrelationships in the netlist. Experimental results on the ISPD2015 benchmarksshow that we achieve an improvement of 10.9% compared to previous methods.

HybridNet: Dual-Branch Fusion of Geometrical and Topological Views for VLSI Congestion Prediction